MWIRSTD: A MWIR Small Target Detection Dataset

TL;DR

This paper introduces MWIRSTD, a new authentic MWIR small target detection dataset with diverse scenes and targets, enabling improved development and evaluation of detection methods in realistic thermal imaging environments.

Contribution

The paper presents MWIRSTD, the first dataset of its kind with authentic MWIR data, diverse targets, and environments, facilitating research in small object detection.

Findings

Traditional methods show limited effectiveness on MWIRSTD.

Deep learning techniques outperform traditional approaches.

The dataset enables comprehensive evaluation of detection algorithms.

Abstract

This paper presents a novel mid-wave infrared (MWIR) small target detection dataset (MWIRSTD) comprising 14 video sequences containing approximately 1053 images with annotated targets of three distinct classes of small objects. Captured using cooled MWIR imagers, the dataset offers a unique opportunity for researchers to develop and evaluate state-of-the-art methods for small object detection in realistic MWIR scenes. Unlike existing datasets, which primarily consist of uncooled thermal images or synthetic data with targets superimposed onto the background or vice versa, MWIRSTD provides authentic MWIR data with diverse targets and environments. Extensive experiments on various traditional methods and deep learning-based techniques for small target detection are performed on the proposed dataset, providing valuable insights into their efficacy. The dataset and code are available at https://github.com/avinres/MWIRSTD.